Semiconductor Process Modeling System and Method

1. A semiconductor process modeling system comprising: a preprocessing component configured to generate tensor data from raw data obtained from semiconductor manufacturing equipment, wherein, when the raw data is expressed as a raw matrix representing values of a plurality of process parameters for each of a plurality of wafers, at least one element of the raw matrix is omitted, wherein, when the tensor data is expressed as a tensor matrix representing values of a plurality of preprocessed process parameters for each of the plurality of wafers, a number of omitted elements of the tensor matrix is less than a number of omitted elements of the raw matrix, and wherein the preprocessing component is configured to generate the tensor data by modifying the raw data based on characteristics of the plurality of process parameters for each of the plurality of wafers.

2. The semiconductor process modeling system of claim 1, wherein the number of omitted elements of the tensor matrix is 0.

3. The semiconductor process modeling system of claim 1, wherein the raw data includes a value of a first process parameter for a first wafer and a value of a second process parameter for a second wafer, and wherein the preprocessing component is configured to generate the tensor data from the raw data so that a value of a preprocessed process parameter for the first wafer is identical to the value of the first process parameter for the first wafer, and a value of the preprocessed process parameter for the second wafer is identical to the value of the second process parameter for the second wafer.

4. The semiconductor process modeling system of claim 3, wherein the preprocessing component is configured to obtain the value of the first process parameter from a first chamber of semiconductor manufacturing equipment in which the first wafer is processed, and obtain the value of the second process parameter from a second chamber of the semiconductor manufacturing equipment in which the second wafer is processed.

5. The semiconductor process modeling system of claim 1, wherein the raw data includes a value of a process parameter for a first wafer, and wherein the preprocessing component is configured to generate the tensor data from the raw data so that a value of a preprocessed process parameter for each of the first wafer and a second wafer is identical to the value of the process parameter for the first wafer.

6. The semiconductor process modeling system of claim 5, wherein the preprocessing component is configured to obtain the value of the process parameter from a chamber of semiconductor manufacturing equipment in which the first wafer and the second wafer are simultaneously processed.

7. The semiconductor process modeling system of claim 1, wherein the raw data includes a value of a process parameter for a lot including a first wafer and a second wafer, and wherein the preprocessing component is configured to generate the tensor data from the raw data so that a value of a preprocessed process parameter for each of the first wafer and the second wafer is identical to the value of the process parameter for the lot.

8. The semiconductor process modeling system of claim 7, wherein the preprocessing component is configured to obtain the value of the process parameter from a chamber of semiconductor manufacturing equipment in which the lot is processed.

9. The semiconductor process modeling system of claim 1, wherein the raw data includes a value of a first process parameter for a first wafer and a value of the first process parameter and a second process parameter for a second wafer, and wherein the preprocessing component is configured to generate the tensor data from the raw data so that the tensor data includes the value of the first process parameter for each of the first wafer and the second wafer, and omits the value of the second process parameter for the second wafer.

10. The semiconductor process modeling system of claim 9, wherein, in the raw data, the value of the second process parameter for the second wafer is calculated from the value of the first process parameter for each of the first wafer and the second wafer.

11. The semiconductor process modeling system of claim 1, further comprising: a modeling component including a model learning subcomponent configured to train a first machine learning model to predict a process result value from at least one of the plurality of preprocessed process parameters.

12. The semiconductor process modeling system of claim 11, wherein the modeling component further includes a variable importance calculation subcomponent configured to calculate importance of the plurality of preprocessed process parameters for the process result value by using the first machine learning model.

13. The semiconductor process modeling system of claim 12, wherein the model learning subcomponent is configured to train a second machine learning model to predict a process result value from a preprocessed process parameter of highest importance among the plurality of preprocessed process parameters.

14. A semiconductor manufacturing system comprising: semiconductor manufacturing equipment configured to process a plurality of wafers; and a semiconductor process modeling system, wherein the semiconductor process modeling system includes: a preprocessing component configured to generate tensor data from raw data obtained from the semiconductor manufacturing equipment; and a modeling component configured to model a semiconductor process by using the tensor data, wherein, when the raw data is expressed as a raw matrix representing values of a plurality of process parameters for each of the plurality of wafers, at least one element of the raw matrix is omitted, and wherein, when the tensor data is expressed as a tensor matrix representing values of a plurality of preprocessed process parameters for each of the plurality of wafers, a number of omitted elements of the tensor matrix is less than a number of omitted elements of the raw matrix, and wherein the preprocessing component is configured to generate the tensor data by modifying the raw data based on characteristics of the plurality of process parameters for each of the plurality of wafers.

15. The semiconductor manufacturing system of claim 14, wherein the raw data includes a value of a first process parameter for a first wafer and a value of a second process parameter for a second wafer, and wherein the preprocessing component is configured to generate the tensor data by merging the first process parameter and the second process parameter into one preprocessed process parameter.

16. The semiconductor manufacturing system of claim 15, wherein the semiconductor manufacturing equipment includes a first chamber and a second chamber, and is configured to process the first wafer in the first chamber and process the second wafer in the second chamber, and wherein the preprocessing component is configured to obtain a value of the first process parameter from the first chamber and a value of the second process parameter from the second chamber.

17. The semiconductor manufacturing system of claim 14, wherein the raw data includes a value of a process parameter for a first wafer, and wherein the preprocessing component is configured to generate the tensor data by replicating the value of the process parameter for the first wafer as a value of a preprocessed process parameter for each of the first wafer and a second wafer.

18. The semiconductor manufacturing system of claim 14, wherein the raw data includes a value of a process parameter for a lot including a first wafer and a second wafer, and wherein the preprocessing component is configured to generate the tensor data by replicating the value of the process parameter for the lot as a value of a preprocessed process parameter for each of the first wafer and the second wafer.

19. The semiconductor manufacturing system of claim 14, wherein the raw data includes a value of a first process parameter for a first wafer and a value of the first process parameter and a second process parameter for a second wafer, and wherein the preprocessing component is configured to generate the tensor data by deleting the value of the second process parameter for the second wafer.

20. A semiconductor process modeling method comprising: obtaining raw data including values of a plurality of process parameters for each of a plurality of wafers from semiconductor manufacturing equipment; and generating tensor data by modifying the raw data based on characteristics of the plurality of process parameters for each of the plurality of wafers, wherein, when the raw data is expressed as a raw matrix representing values of the plurality of process parameters for each of the plurality of wafers, at least one element of the raw matrix is omitted, and wherein, when the tensor data is expressed as a tensor matrix representing values of a plurality of preprocessed process parameters for each of the plurality of wafers, a number of omitted elements of the tensor matrix is less than a number of omitted elements of the raw matrix.